Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/jnarowski/agentcmd/list-specsgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00013 | $0.02939 |
| Opus 5 | $0.00006 | $0.01470 |
| Sonnet 5 | $0.00003 | $0.00588 |
| Haiku 4.5 | $0.00001 | $0.00294 |
Grade A, and why
list-specs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List Specs
List all specs in the .agent/specs/ directory, organized by workflow folder and optionally filtered by status field. Uses index.json for fast lookups of timestamp ID specs.
Variables
- $folder: $1 (optional) - Filter by folder: "backlog", "todo", "done", or "all" (defaults to "all")
- $status: $2 (optional) - Filter by status field: "draft", "ready", "in-progress", "review", "completed", or "any" (defaults to "any")
- --search: (optional) - Search keyword to fuzzy match in spec names/paths
- --sort: (optional) - Sort field: "created", "updated", "id", "complexity", "phases", or "tasks" (defaults to "created")
Instructions
- Read index.json for fast lookup of timestamp ID specs
- Parse spec files to extract metadata (Status field) only when status filtering is needed
- Filter by folder if specified
- Filter by status if specified
- Search by keyword if specified (fuzzy match in spec names)
- Sort results by specified field
- Group specs in same folder for multi-spec folders
- Display results organized by folder with spec ID, feature name, created/updated dates, and status
Workflow
-
Load Specs from Index
- Read
.agent/specs/index.json - For each spec in index, extract:
- Spec ID (key in specs object)
- Path (contains both location and folder name)
- Status (cached from spec.md)
- Created datetime
- Updated datetime
- Location: Derive from path by splitting on '/' (e.g., "todo/1-log-streaming" → location="todo", folder="1-log-streaming")
- Read
-
Apply Filters
-
Folder filter:
- If $folder is "backlog": Only show specs where location (from path) is "backlog"
- If $folder is "todo": Only show specs where location is "todo"
- If $folder is "done": Only show specs where location is "done"
- If $folder is "all" or not provided: Show all specs
-
Status filter:
- If $status is specified and not "any":
- Use cached status from index.json
- Only include specs matching that status
- If $status is "any" or not provided: Show all specs
- If a spec has no status field in index, treat it as status "unknown"
- If $status is specified and not "any":
-
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 345 lines · 13 tokens per session scan A 291e41fcc789
list-specs is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 2,939 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.